Data visualization for fraud detection: Practice implications and a call for future research

Abstract

Analysis of data to detect transaction anomalies is an important fraud detection procedure. Interactive data visualization tools that allow the investigator to change the representation of data from text to graphics and filter out subsets of transactions for further investigation have substantial potential for making the detection of fraudulent transactions more efficient and effective. However, little research to date has directly examined the efficacy of data visualization techniques for fraud detection. In this paper, we develop a theoretical framework to predict when and how investigators might use data visualization techniques to detect fraudulent transactions. We use this framework to develop testable propositions and research questions related to this topic. The paper concludes by discussing how academic research might proceed in investigating the efficacy of interactive data visualization tools for fraud detection.